Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mental health professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    लों
    0.64
     FEES
    0.62
    ع
    0.62
    נו
    0.59
     corpora
    0.59
     stripos
    0.59
    锢
    0.57
    шибка
    0.55
    ╕
    0.55
     taip
    0.54
    POSITIVE LOGITS
    <0x80>
    0.65
     всего
    0.64
    ことになる
    0.59
    е
    0.58
    toolStrip
    0.57
     พิจิก
    0.56
     значение
    0.56
    𝑛
    0.54
     psychologist
    0.54
     distressing
    0.54
    Act Density 0.506%

    No Known Activations